FPED: A Functional-Network Prior-Guided Mixture-of-Experts Framework for Interpretable Brain Decoding
Quick Take
FPED introduces a novel framework for interpretable brain decoding using functional network priors.
Key Points
- Models functional brain networks as specialized experts.
- Achieves competitive performance with only 0.68B parameters.
- Provides transparent neuroscientific interpretability.
📖 Reader Mode
~2 min readAbstract:Visual image reconstruction from functional Magnetic Resonance Imaging (fMRI) is a fundamental task in brain decoding, providing a crucial pathway for understanding human perceptual mechanisms and developing advanced brain-computer interfaces (BCIs). However, most current methods simply flatten fMRI signals from localized visual cortices into one-dimensional (1D) vectors, mapping them directly into latent spaces such as that of Contrastive Language-Image Pre-training (CLIP). This paradigm not only disrupts the inherent network topology of the brain-leading to limited neuroscientific interpretability-but also overlooks the synergistic contributions of other distributed functional networks in processing high-level visual semantics. To address these limitations, we propose FPED, a Functional-Network Prior-Guided Mixture of Experts (MoE) framework for interpretable brain decoding. FPED explicitly models different functional brain networks as specialized experts and employs adaptive routing to capture their complementary contributions to visual semantic understanding. Unlike conventional homogeneous decoding paradigms, our framework incorporates neurobiologically grounded priors to enable structured and interpretable network-level representation learning. Experimental results demonstrate that FPED achieves highly competitive semantic reconstruction performance with only 0.68B parameters. The learned routing dynamics reveal biologically meaningful correspondence between functional brain networks and modality-specific semantic processing, providing transparent neuroscientific interpretability. This suggests that brain network-aware expert modeling is a promising direction for bridging neural decoding and biologically inspired artificial intelligence.
| Comments: | 15 pages,4 figures |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2605.19279 [cs.CV] |
| (or arXiv:2605.19279v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2605.19279 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Pengcheng Shi [view email]
[v1]
Tue, 19 May 2026 02:53:49 UTC (5,543 KB)
— Originally published at arxiv.org
More from arXiv cs.CV
See more →GeoSym127K: Scalable Symbolically-verifiable Synthesis for Multimodal Geometric Reasoning
GeoSym127K introduces a scalable neuro-symbolic framework for enhanced geometric reasoning in multimodal models.